You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/langchain/document_loaders/college_confidential.py

17 lines
562 B
Python

"""Loader that loads College Confidential."""
from typing import List
from langchain.docstore.document import Document
from langchain.document_loaders.web_base import WebBaseLoader
class CollegeConfidentialLoader(WebBaseLoader):
"""Loader that loads College Confidential webpages."""
def load(self) -> List[Document]:
"""Load webpage."""
soup = self.scrape()
text = soup.select_one("main[class='skin-handler']").text
metadata = {"source": self.web_path}
return [Document(page_content=text, metadata=metadata)]